Presentation is loading. Please wait.

Presentation is loading. Please wait.

Miguel Tavares Coimbra

Published by瑛曲 马 Modified over 5 years ago

Similar presentations

Presentation on theme: "Miguel Tavares Coimbra"— Presentation transcript:

1 Miguel Tavares Coimbra
VC 18/19 – TP14 Pattern Recognition Mestrado em Ciência de Computadores Mestrado Integrado em Engenharia de Redes e Sistemas Informáticos Miguel Tavares Coimbra

2 Outline Introduction to Pattern Recognition
Statistical Pattern Recognition Classifiers VC 18/19 - TP14 - Pattern Recognition

3 Topic: Introduction to Pattern Recognition
Statistical Pattern Recognition Classifiers VC 18/19 - TP14 - Pattern Recognition

4 This is a horse http://www.flickr.com/photos/kimbar/2027234083/
VC 18/19 - TP14 - Pattern Recognition

5 This is a horse http://www.flickr.com/photos/genewolf/2031802050/
VC 18/19 - TP14 - Pattern Recognition

6 This is a... Horse? VC 18/19 - TP14 - Pattern Recognition

7 Decisions I can manipulate images. I want to make decisions!
Classify / Identify features. Recognize patterns. VC 18/19 - TP14 - Pattern Recognition

8 One definition Pattern recognition How do I do this so well?
"the act of taking in raw data and taking an action based on the category of the data". Wikipedia How do I do this so well? How can I make machines do this? VC 18/19 - TP14 - Pattern Recognition

9 The problem Do you ‘see’ a horse? What a computer sees
VC 18/19 - TP14 - Pattern Recognition

10 Mathematics We only deal with numbers. Very complex problem!!
How do we represent knowledge? How do we represent visual features? How do we classify them? Very complex problem!! Let’s break it into smaller ones... VC 18/19 - TP14 - Pattern Recognition

11 Typical PR system Sensor Feature Extraction Classifier
Does the actual job of classifying or describing observations, relying on the extracted features. Feature Extraction Computes numeric or symbolic information from the observations; Sensor Gathers the observations to be classified or described VC 18/19 - TP14 - Pattern Recognition

12 Sensor In our specific case: Image acquiring mechanism.
Let’s assume we don’t control it. One observation = One Image Video = Multiple Observations VC 18/19 - TP14 - Pattern Recognition

13 Feature Extraction What exactly are features? These vary a lot!
Colour, texture, shape, etc. Animal with 4 legs. Horse. Horse jumping. These vary a lot! Some imply some sort of ‘recognition’ e.g. How do I know the horse is jumping? VC 18/19 - TP14 - Pattern Recognition

14 Broad classification of features
Low-level Colour, texture Middle-level Object with head and four legs. Object moving up. Horse High-level Horse jumping. Horse competition. VC 18/19 - TP14 - Pattern Recognition

15 Low-level features Objective
Directly reflect specific image and video features. Colour Texture Shape Motion Etc. VC 18/19 - TP14 - Pattern Recognition

16 Middle-level features
Some degree of subjectivity They are typically one solution of a problem with multiple solutions. Examples: Segmentation Optical Flow Identification Etc. VC 18/19 - TP14 - Pattern Recognition

17 How do humans do this so well?
High-level features Semantic Interpretation Knowledge Context Examples: This person suffers from epilepsy. The virus attacks the cell with some degree of intelligence. This person is running from that one. How do humans do this so well? VC 18/19 - TP14 - Pattern Recognition

18 How do i cross this bridge?
The semantic gap Fundamental problem of current research! High-level: Interpretation Decision -Understanding … Low-level: Colour Texture Shape … Now what?? How do i cross this bridge? VC 18/19 - TP14 - Pattern Recognition

19 Middle-Level Features
Features & Decisions Various Possible Solutions Low-Level Features Middle-Level Features High-Level Features How do I decide? Decision Decision One Solution VC 18/19 - TP14 - Pattern Recognition

20 Middle-Level Features
Classification Middle-Level Features High-Level Features Horse Upward Motion Rider Classifier Horse Jumping Competition M inputs, N outputs VC 18/19 - TP14 - Pattern Recognition

21 Layers of classification
First layer of classificaiton Second layer of classificaiton Brown Four legs Head ... Horse Upward Motion Rider Horse Jumping Competition VC 18/19 - TP14 - Pattern Recognition

22 Classifiers How do I map my M inputs to my N outputs?
Mathematical tools: Distance-based classifiers. Rule-based classifiers. Neural Networks. Support Vector Machines ... VC 18/19 - TP14 - Pattern Recognition

23 Types of PR methods Statistical pattern recognition
based on statistical characterizations of patterns, assuming that the patterns are generated by a probabilistic system. Syntactical (or structural) pattern recognition based on the structural interrelationships of features. VC 18/19 - TP14 - Pattern Recognition

24 Topic: Statistical Pattern Recognition
Introduction to Pattern Recognition Statistical Pattern Recognition Classifiers VC 18/19 - TP14 - Pattern Recognition

25 Is Porto in Portugal? VC 18/19 - TP14 - Pattern Recognition

26 Porto is in Portugal I want to make decisions. I know certain things.
Is Porto in Portugal? I know certain things. A world map including cities and countries. I can make this decision! Porto is in Portugal. I had enough a priori knowledge to make this decision. VC 18/19 - TP14 - Pattern Recognition

27 What if I don’t have a map?
I still want to make this decision. I observe: Amarante has coordinates x1,y1 and is in Portugal. Viseu has coordinates x2, y2 and is in Portugal. Vigo has coordinates x3, y3 and is in Spain. I classify: Porto is close to Amarante and Viseu so Porto is in Portugal. What if I try to classify Valença? VC 18/19 - TP14 - Pattern Recognition

28 Statistical PR I used statistics to make a decision.
I can make decisions even when I don’t have full a priori knowledge of the whole process. I can make mistakes. How did I recognize this pattern? I learned from previous observations where I knew the classification result. I classified a new observation. What pattern? VC 18/19 - TP14 - Pattern Recognition

29 Back to the Features Feature Fi Feature Fi with N values.
Feature vector F with M features. Naming conventions: Elements of a feature vector are called coefficients. Features may have one or more coefficients. Feature vectors may have one or more features. VC 18/19 - TP14 - Pattern Recognition

30 Back to our Porto example
I’ve classified that Porto is in Portugal. What feature did I use? Spatial location Let’s get more formal I’ve defined a feature vector F with one feature F1, which has two coefficients f1x, f1y. VC 18/19 - TP14 - Pattern Recognition

31 Feature Space Feature Vector Feature Space Two total coefficients.
Can be seen as a feature ‘space’ with two orthogonal axis. Feature Space Hyper-space with N dimensions where N is the total number of coefficients of my feature vector. VC 18/19 - TP14 - Pattern Recognition

32 I know the border is here
A Priori Knowledge I have a precise model of my feature space based on a priori knowledge. City is in Spain if F1Y>23 Great models = Great classifications. F1Y(London) = 100 London is in Spain (??) I know the border is here Porto is in Portugal! VC 18/19 - TP14 - Pattern Recognition

33 What if I don’t have a model?
I need to learn from observations. Derive a model. Direct classification. Training stage. Learn model parameters. Classification ‘Learned’ Model VC 18/19 - TP14 - Pattern Recognition

34 Classes In our example, cities can belong to:
Portugal Spain I have two classes of cities. A class represents a sub-space of my feature space. SPAIN PORTUGAL VC 18/19 - TP14 - Pattern Recognition

35 Classifiers A Classifier C maps a class into the feature space.
Various types of classifiers. Nearest-Neighbours. Bayesian. Soft-computing machines. Etc... VC 18/19 - TP14 - Pattern Recognition

36 Topic: Classifiers Introduction to Pattern Recognition
Statistical Pattern Recognition Classifiers VC 18/19 - TP14 - Pattern Recognition

37 Distance to Mean I can represent a class by its mean feature vector.
To classify a new object, I choose the class with the closest mean feature vector. Different distance measures! Euclidean Distance VC 18/19 - TP14 - Pattern Recognition

38 Possible Distance Measures
L1 Distance Euclidean Distance (L2 Distance) L1 or Taxicab Distance VC 18/19 - TP14 - Pattern Recognition

39 Gaussian Distribution
Defined by two parameters: Mean: μ Variance: σ2 Great approximation to the distribution of many phenomena. Central Limit Theorem VC 18/19 - TP14 - Pattern Recognition

40 Multivariate Distribution
For N dimensions: Mean feature vector: Covariance Matrix: VC 18/19 - TP14 - Pattern Recognition

41 Mahalanobis Distance Based on the covariance of coefficients.
Superior to the Euclidean distance. VC 18/19 - TP14 - Pattern Recognition

42 K-Nearest Neighbours Algorithm Characteristics
Choose the closest K neighbours to a new observation. Classify the new object based on the class of these K objects. Characteristics Assumes no model. Does not scale very well... VC 18/19 - TP14 - Pattern Recognition

43 Resources Gonzalez & Woods, 3rd Ed, Chapter 12.
Andrew Moore, Statistic Data Mining Tutorial, VC 18/19 - TP14 - Pattern Recognition

Download ppt "Miguel Tavares Coimbra"

Similar presentations

Applications of one-class classification

Applications of one-class classification
Pseudo-Relevance Feedback For Multimedia Retrieval By Rong Yan, Alexander G. and Rong Jin Mwangi S. Kariuki 2008-11629.

Pseudo-Relevance Feedback For Multimedia Retrieval By Rong Yan, Alexander G. and Rong Jin Mwangi S. Kariuki
Image classification Given the bag-of-features representations of images from different classes, how do we learn a model for distinguishing them?

Image classification Given the bag-of-features representations of images from different classes, how do we learn a model for distinguishing them?
Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties.

Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties.
Lecture 20 Object recognition I

Lecture 20 Object recognition I
CS292 Computational Vision and Language Pattern Recognition and Classification.

CS292 Computational Vision and Language Pattern Recognition and Classification.
Chapter 2: Pattern Recognition

Chapter 2: Pattern Recognition
Mestrado em Ciência de Computadores Mestrado Integrado em Engenharia de Redes e Sistemas Informáticos VC 14/15 – TP9 Region-Based Segmentation Miguel Tavares.

Mestrado em Ciência de Computadores Mestrado Integrado em Engenharia de Redes e Sistemas Informáticos VC 14/15 – TP9 Region-Based Segmentation Miguel Tavares.
MACHINE LEARNING 6. Multivariate Methods 1. Based on E Alpaydın 2004 Introduction to Machine Learning © The MIT Press (V1.1) 2 Motivating Example  Loan.

MACHINE LEARNING 6. Multivariate Methods 1. Based on E Alpaydın 2004 Introduction to Machine Learning © The MIT Press (V1.1) 2 Motivating Example  Loan.
Mestrado em Ciência de Computadores Mestrado Integrado em Engenharia de Redes e Sistemas Informáticos VC 14/15 – TP3 Digital Images Miguel Tavares Coimbra.

Mestrado em Ciência de Computadores Mestrado Integrado em Engenharia de Redes e Sistemas Informáticos VC 14/15 – TP3 Digital Images Miguel Tavares Coimbra.
嵌入式視覺 Pattern Recognition for Embedded Vision Template matching Statistical / Structural Pattern Recognition Neural networks.

嵌入式視覺 Pattern Recognition for Embedded Vision Template matching Statistical / Structural Pattern Recognition Neural networks.
Principles of Pattern Recognition

Principles of Pattern Recognition
ECE 8443 – Pattern Recognition LECTURE 03: GAUSSIAN CLASSIFIERS Objectives: Normal Distributions Whitening Transformations Linear Discriminants Resources.

ECE 8443 – Pattern Recognition LECTURE 03: GAUSSIAN CLASSIFIERS Objectives: Normal Distributions Whitening Transformations Linear Discriminants Resources.
COMMON EVALUATION FINAL PROJECT Vira Oleksyuk ECE 8110: Introduction to machine Learning and Pattern Recognition.

COMMON EVALUATION FINAL PROJECT Vira Oleksyuk ECE 8110: Introduction to machine Learning and Pattern Recognition.
ECE 8443 – Pattern Recognition ECE 8527 – Introduction to Machine Learning and Pattern Recognition LECTURE 03: GAUSSIAN CLASSIFIERS Objectives: Whitening.

ECE 8443 – Pattern Recognition ECE 8527 – Introduction to Machine Learning and Pattern Recognition LECTURE 03: GAUSSIAN CLASSIFIERS Objectives: Whitening.
1 Pattern Recognition Concepts How should objects be represented? Algorithms for recognition/matching * nearest neighbors * decision tree * decision functions.

1 Pattern Recognition Concepts How should objects be represented? Algorithms for recognition/matching * nearest neighbors * decision tree * decision functions.
Mestrado em Ciência de Computadores Mestrado Integrado em Engenharia de Redes e Sistemas Informáticos VC 14/15 – TP19 Neural Networks & SVMs Miguel Tavares.

Mestrado em Ciência de Computadores Mestrado Integrado em Engenharia de Redes e Sistemas Informáticos VC 14/15 – TP19 Neural Networks & SVMs Miguel Tavares.
Data Mining: Classification & Predication Hosam Al-Samarraie, PhD. Centre for Instructional Technology & Multimedia Universiti Sains Malaysia.

Data Mining: Classification & Predication Hosam Al-Samarraie, PhD. Centre for Instructional Technology & Multimedia Universiti Sains Malaysia.
Image Classification 영상분류

Image Classification 영상분류
Mestrado em Ciência de Computadores Mestrado Integrado em Engenharia de Redes e Sistemas Informáticos VC 14/15 – TP8 Segmentation Miguel Tavares Coimbra.

Mestrado em Ciência de Computadores Mestrado Integrado em Engenharia de Redes e Sistemas Informáticos VC 14/15 – TP8 Segmentation Miguel Tavares Coimbra.

Similar presentations

Ads by Google